PM 2.5 in Germany

library(tidyverse)
library(lubridate)
library(ggplot2)

url <- 'http://berkeleyearth.lbl.gov/air-quality/maps/cities/Thailand/Chiang_Mai/Chiang_Mai.txt'
df <- read_tsv(url,skip=10, col_names = FALSE)

Parsed with column specification:
cols(
  X1 = col_double(),
  X2 = col_double(),
  X3 = col_double(),
  X4 = col_double(),
  X5 = col_double(),
  X6 = col_double(),
  X7 = col_double()
)

df

—— Summarized Data (Reserved) ——

—— Visualized Data ——

## entire data

by date for each month

By month for each year

df %>% 
  mutate(year = year(local_dt),
         month = month(local_dt),
         date = date(local_dt)) %>%
  group_by(year,month) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  ggplot(aes(month, y = avg_pm , color = as.factor(year)))+geom_line()

## create heat map

df %>% 
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = day(date),
         month = month(date),
         year = year(date)) %>%
  ggplot(aes(day, y=month, fill=avg_pm)) + geom_tile()

## add factor to map, make it display by day

df %>% 
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = as.factor(month(date)),
         year = as.factor(year(date))) %>%
  ggplot(aes(day, y=month, fill=avg_pm)) + geom_tile()

## add border and set a color

df %>% 
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = as.factor(month(date)),
         year = as.factor(year(date))) %>%
  ggplot(aes(day, y=month, fill=avg_pm)) +
  geom_tile(color="white") +
  scale_fill_gradient(low = "green" , high = 'red')

adjust cell scale

df %>% 
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = as.factor(month(date)),
         year = as.factor(year(date))) %>%
  ggplot(aes(day, y=month, fill=avg_pm)) +
  geom_tile(color="white") +
  scale_fill_gradient(low = "green" , high = 'red') +
  coord_equal()

set interval factor for avg pm 2.5

df %>% 
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = as.factor(month(date)),
         year = as.factor(year(date))) %>%
  mutate(pm_lv = cut(avg_pm, ## create new column to classify level of smog
         breaks = c(0,12,35.4,55.4,150.4,250.4,350.4),
         labels = c('good','moderate','unheathy for sensitive groups'
                    ,'unheathy','very unheathy','hazardous'))) %>%
  ggplot(aes(day, y=month, fill=pm_lv)) + ## replace avg_pm with pm_level
  geom_tile(color="white") +
  scale_fill_manual(values = c('green','yellow','orange','red','magenta', 'violet'))+
  coord_equal()

separate by year

df %>% 
  filter(year(local_dt) > 2015) %>%
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = as.factor(month(date)),
         year = as.factor(year(date))) %>%
  mutate(pm_lv = cut(avg_pm, 
         breaks = c(0,12,35.4,55.4,150.4,250.4,350.4),
         labels = c('good','moderate','unheathy for sensitive groups'
                    ,'unheathy','very unheathy','hazardous'))) %>%
  ggplot(aes(day, y=month, fill=pm_lv)) + 
  geom_tile(color="white") +
  facet_grid(year~.) + ## separate by year
  scale_fill_manual(values = c('green','yellow','orange','red','magenta', 'violet'))+
  coord_equal()

reverse month -> make less value on top

df %>% 
  filter(year(local_dt) > 2015) %>%
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = fct_rev(as_factor(month(date))),  ## remove as.factor and add fct_rev() to month and make it factor using as_factor
         year = as.factor(year(date))) %>%
  mutate(pm_lv = cut(avg_pm, 
         breaks = c(0,12,35.4,55.4,150.4,250.4,350.4),
         labels = c('good','moderate','unheathy for sensitive groups'
                    ,'unheathy','very unheathy','hazardous'))) %>%
  ggplot(aes(day, y=month, fill=pm_lv)) + 
  xlab("Day") + ylab("Month") +
  geom_tile(color="white") +
  facet_grid(year~.) + 
  scale_fill_manual(values = c('green','yellow','orange','red','magenta', 'violet'))+
  coord_equal()

add tooltip

tt <- df %>%  ## put ggplot in to tt (tooltip)
  filter(year(local_dt) > 2017) %>%
  mutate(date = date(local_dt)) %>%
  group_by(date) %>%
  summarize(avg_pm = mean(PM2_5)) %>%
  mutate(day = as.factor(day(date)),
         month = fct_rev(as_factor(month(date))),  
         year = as.factor(year(date))) %>%
  mutate(pm_lv = cut(avg_pm, 
         breaks = c(0,12,35.4,55.4,150.4,250.4,350.4),
         labels = c('good','moderate','unheathy for sensitive groups'
                    ,'unheathy','very unheathy','hazardous'))) %>%
  ggplot(aes(day, y=month, fill=pm_lv)) + 
  xlab("Day") + ylab("Month") +
  geom_tile(color="white") +
  facet_grid(year~.) + 
  scale_fill_manual(values = c('green','yellow','orange','red','magenta', 'violet'))+
  coord_equal()

ggplotly(tt) # display ggplot with tooltip